Enhancing Perception Quality in Remote Sensing Image Compression via Invertible Neural Network

TL;DR

This paper introduces INN-RSIC, an invertible neural network approach that enhances the perceptual quality of remote sensing images at low bitrates by modeling and reversing compression distortions.

Contribution

The paper proposes a novel invertible neural network framework for remote sensing image compression that improves perceptual quality by effectively modeling and reversing compression distortions.

Findings

Outperforms state-of-the-art methods in perception quality

Effectively models compression distortion as Gaussian variables

Enhances images using inverse network with resampled Gaussian variables

Abstract

Decoding remote sensing images to achieve high perceptual quality, particularly at low bitrates, remains a significant challenge. To address this problem, we propose the invertible neural network-based remote sensing image compression (INN-RSIC) method. Specifically, we capture compression distortion from an existing image compression algorithm and encode it as a set of Gaussian-distributed latent variables via INN. This ensures that the compression distortion in the decoded image becomes independent of the ground truth. Therefore, by leveraging the inverse mapping of INN, we can input the decoded image along with a set of randomly resampled Gaussian distributed variables into the inverse network, effectively generating enhanced images with better perception quality. To effectively learn compression distortion, channel expansion, Haar transformation, and invertible blocks are employed to construct the INN. Additionally, we introduce a quantization module (QM) to mitigate the impact of format conversion, thus enhancing the framework's generalization and improving the perceptual quality of enhanced images. Extensive experiments demonstrate that our INN-RSIC significantly outperforms the existing state-of-the-art traditional and deep learning-based image compression methods in terms of perception quality.